From a323aa9385ebaa5b9b8e290e1bb0cc37c9e3c241 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 18 四月 2023 14:43:55 +0800
Subject: [PATCH] docs
---
docs/recipe/vad_recipe.md | 0
docs/runtime/grpc_cpp.md | 0
docs/modescope_pipeline/vad_pipeline.md | 14 +++
docs/index.rst | 34 +++++---
docs/runtime/onnxruntime_python.md | 0
docs/runtime/libtorch_python.md | 0
docs/modescope_pipeline/lm_pipeline.md | 14 +++
docs/modescope_pipeline/asr_pipeline.md | 14 +++
docs/recipe/asr_recipe.md | 0
docs/recipe/sv_recipe.md | 0
docs/runtime/onnxruntime_cpp.md | 1
/dev/null | 1
docs/runtime/websocket_python.md | 1
docs/recipe/punc_recipe.md | 0
docs/recipe/lm_recipe.md | 0
docs/runtime/export.md | 1
docs/modelscope_models.md | 2
docs/runtime/grpc_python.md | 1
docs/modescope_pipeline/modelscope_usages.md | 0
docs/modescope_pipeline/sv_pipeline.md | 14 +++
docs/modescope_pipeline/punc_pipeline.md | 14 +++
docs/huggingface_models.md | 94 +++++++++++++++++++++++
docs/modescope_pipeline/quick_start.md | 6 +
docs/modescope_pipeline/tp_pipeline.md | 14 +++
24 files changed, 210 insertions(+), 15 deletions(-)
diff --git a/docs/export.md b/docs/export.md
deleted file mode 120000
index 592b12d..0000000
--- a/docs/export.md
+++ /dev/null
@@ -1 +0,0 @@
-../funasr/export/README.md
\ No newline at end of file
diff --git a/docs/grpc_python.md b/docs/grpc_python.md
deleted file mode 120000
index 792fccd..0000000
--- a/docs/grpc_python.md
+++ /dev/null
@@ -1 +0,0 @@
-../funasr/runtime/python/grpc/Readme.md
\ No newline at end of file
diff --git a/docs/huggingface_models.md b/docs/huggingface_models.md
new file mode 100644
index 0000000..61754eb
--- /dev/null
+++ b/docs/huggingface_models.md
@@ -0,0 +1,94 @@
+# Pretrained Models on Huggingface
+
+## Model License
+- Apache License 2.0
+
+## Model Zoo
+Here we provided several pretrained models on different datasets. The details of models and datasets can be found on [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition).
+
+### Speech Recognition Models
+#### Paraformer Models
+
+| Model Name | Language | Training Data | Vocab Size | Parameter | Offline/Online | Notes |
+|:--------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
+| [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Duration of input wav <= 20s |
+| [Paraformer-large-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which ould deal with arbitrary length input wav |
+| [paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords. |
+| [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary) | CN & EN | Alibaba Speech Data (50000hours) | 8358 | 68M | Offline | Duration of input wav <= 20s |
+| [Paraformer-online](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary) | CN & EN | Alibaba Speech Data (50000hours) | 8404 | 68M | Online | Which could deal with streaming input |
+| [Paraformer-tiny](https://www.modelscope.cn/models/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/summary) | CN | Alibaba Speech Data (200hours) | 544 | 5.2M | Offline | Lightweight Paraformer model which supports Mandarin command words recognition |
+| [Paraformer-aishell](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-aishell1-pytorch/summary) | CN | AISHELL (178hours) | 4234 | 43M | Offline | |
+| [ParaformerBert-aishell](https://modelscope.cn/models/damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/summary) | CN | AISHELL (178hours) | 4234 | 43M | Offline | |
+| [Paraformer-aishell2](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary) | CN | AISHELL-2 (1000hours) | 5212 | 64M | Offline | |
+| [ParaformerBert-aishell2](https://www.modelscope.cn/models/damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary) | CN | AISHELL-2 (1000hours) | 5212 | 64M | Offline | |
+
+
+#### UniASR Models
+
+| Model Name | Language | Training Data | Vocab Size | Parameter | Offline/Online | Notes |
+|:--------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
+| [UniASR](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8358 | 100M | Online | UniASR streaming offline unifying models |
+| [UniASR-large](https://modelscope.cn/models/damo/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8358 | 220M | Offline | UniASR streaming offline unifying models |
+| [UniASR Burmese](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/summary) | Burmese | Alibaba Speech Data (? hours) | 696 | 95M | Online | UniASR streaming offline unifying models |
+| [UniASR Hebrew](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/summary) | Hebrew | Alibaba Speech Data (? hours) | 1085 | 95M | Online | UniASR streaming offline unifying models |
+| [UniASR Urdu](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/summary) | Urdu | Alibaba Speech Data (? hours) | 877 | 95M | Online | UniASR streaming offline unifying models |
+
+#### Conformer Models
+
+| Model Name | Language | Training Data | Vocab Size | Parameter | Offline/Online | Notes |
+|:----------------------------------------------------------------------------------------------------------------------:|:--------:|:---------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
+| [Conformer](https://modelscope.cn/models/damo/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/summary) | CN | AISHELL (178hours) | 4234 | 44M | Offline | Duration of input wav <= 20s |
+| [Conformer](https://www.modelscope.cn/models/damo/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary) | CN | AISHELL-2 (1000hours) | 5212 | 44M | Offline | Duration of input wav <= 20s |
+
+
+#### RNN-T Models
+
+### Multi-talker Speech Recognition Models
+
+#### MFCCA Models
+
+| Model Name | Language | Training Data | Vocab Size | Parameter | Offline/Online | Notes |
+|:-------------------------------------------------------------------------------------------------------------:|:--------:|:------------------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
+| [MFCCA](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary) | CN | AliMeeting銆丄ISHELL-4銆丼imudata (917hours) | 4950 | 45M | Offline | Duration of input wav <= 20s, channel of input wav <= 8 channel |
+
+
+
+### Voice Activity Detection Models
+
+| Model Name | Training Data | Parameters | Sampling Rate | Notes |
+|:----------------------------------------------------------------------------------------------:|:----------------------------:|:----------:|:-------------:|:------|
+| [FSMN-VAD](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) | Alibaba Speech Data (5000hours) | 0.4M | 16000 | |
+| [FSMN-VAD](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-8k-common/summary) | Alibaba Speech Data (5000hours) | 0.4M | 8000 | |
+
+### Punctuation Restoration Models
+
+| Model Name | Training Data | Parameters | Vocab Size| Offline/Online | Notes |
+|:--------------------------------------------------------------------------------------------------------------------------:|:----------------------------:|:----------:|:----------:|:--------------:|:------|
+| [CT-Transformer](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary) | Alibaba Text Data | 70M | 272727 | Offline | offline punctuation model |
+| [CT-Transformer](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727/summary) | Alibaba Text Data | 70M | 272727 | Online | online punctuation model |
+
+### Language Models
+
+| Model Name | Training Data | Parameters | Vocab Size | Notes |
+|:----------------------------------------------------------------------------------------------------------------------:|:----------------------------:|:----------:|:----------:|:------|
+| [Transformer](https://www.modelscope.cn/models/damo/speech_transformer_lm_zh-cn-common-vocab8404-pytorch/summary) | Alibaba Speech Data (?hours) | 57M | 8404 | |
+
+### Speaker Verification Models
+
+| Model Name | Training Data | Parameters | Number Speaker | Notes |
+|:-------------------------------------------------------------------------------------------------------------:|:-----------------:|:----------:|:----------:|:------|
+| [Xvector](https://www.modelscope.cn/models/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/summary) | CNCeleb (1,200 hours) | 17.5M | 3465 | Xvector, speaker verification, Chinese |
+| [Xvector](https://www.modelscope.cn/models/damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch/summary) | CallHome (60 hours) | 61M | 6135 | Xvector, speaker verification, English |
+
+### Speaker diarization Models
+
+| Model Name | Training Data | Parameters | Notes |
+|:----------------------------------------------------------------------------------------------------------------:|:-------------------:|:----------:|:------|
+| [SOND](https://www.modelscope.cn/models/damo/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/summary) | AliMeeting (120 hours) | 40.5M | Speaker diarization, profiles and records, Chinese |
+| [SOND](https://www.modelscope.cn/models/damo/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch/summary) | CallHome (60 hours) | 12M | Speaker diarization, profiles and records, English |
+
+### Timestamp Prediction Models
+
+| Model Name | Language | Training Data | Parameters | Notes |
+|:--------------------------------------------------------------------------------------------------:|:--------------:|:-------------------:|:----------:|:------|
+| [TP-Aligner](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) | CN | Alibaba Speech Data (50000hours) | 37.8M | Timestamp prediction, Mandarin, middle size |
diff --git a/docs/index.rst b/docs/index.rst
index ae75c3f..e6fe51d 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -19,10 +19,10 @@
:maxdepth: 1
:caption: Recipe
- ./asr_recipe.md
- ./sv_recipe.md
- ./punc_recipe.md
- ./vad_recipe.md
+ ./recipe/asr_recipe.md
+ ./recipe/sv_recipe.md
+ ./recipe/punc_recipe.md
+ ./recipe/vad_recipe.md
.. toctree::
:maxdepth: 1
@@ -34,22 +34,30 @@
:maxdepth: 1
:caption: Runtime
- ./export.md
- ./onnxruntime_python.md
- ./onnxruntime_cpp.md
- ./libtorch_python.md
- ./grpc_python.md
- ./grpc_cpp.md
- ./websocket_python.md
+ ./runtime/export.md
+ ./runtime/onnxruntime_python.md
+ ./runtime/onnxruntime_cpp.md
+ ./runtime/libtorch_python.md
+ ./runtime/grpc_python.md
+ ./runtime/grpc_cpp.md
+ ./runtime/websocket_python.md
+.. toctree::
+ :maxdepth: 1
+ :caption: Model Zoo
+ ./modelscope_models.md
+ ./huggingface_models.md
.. toctree::
:maxdepth: 1
:caption: ModelScope pipeline
- ./modelscope_models.md
- ./modelscope_usages.md
+ ./modescope_pipeline/quick_start.md
+ ./modescope_pipeline/asr_pipeline.md
+ ./modescope_pipeline/vad_pipeline.md
+ ./modescope_pipeline/punc_pipeline.md
+ ./modescope_pipeline/sv_pipeline.md
.. toctree::
:maxdepth: 1
diff --git a/docs/modelscope_models.md b/docs/modelscope_models.md
index 6c88b69..b35d625 100644
--- a/docs/modelscope_models.md
+++ b/docs/modelscope_models.md
@@ -1,4 +1,4 @@
-# Pretrained models
+# Pretrained Models on ModelScope
## Model License
- Apache License 2.0
diff --git a/docs/modescope_pipeline/asr_pipeline.md b/docs/modescope_pipeline/asr_pipeline.md
new file mode 100644
index 0000000..cb81871
--- /dev/null
+++ b/docs/modescope_pipeline/asr_pipeline.md
@@ -0,0 +1,14 @@
+# Speech Recognition
+
+## Inference with pipeline
+### Quick start
+#### Inference with you data
+#### Inference with multi-threads on CPU
+#### Inference with multi GPU
+
+## Finetune with pipeline
+### Quick start
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/docs/modescope_pipeline/lm_pipeline.md b/docs/modescope_pipeline/lm_pipeline.md
new file mode 100644
index 0000000..cb81871
--- /dev/null
+++ b/docs/modescope_pipeline/lm_pipeline.md
@@ -0,0 +1,14 @@
+# Speech Recognition
+
+## Inference with pipeline
+### Quick start
+#### Inference with you data
+#### Inference with multi-threads on CPU
+#### Inference with multi GPU
+
+## Finetune with pipeline
+### Quick start
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/docs/modelscope_usages.md b/docs/modescope_pipeline/modelscope_usages.md
similarity index 100%
rename from docs/modelscope_usages.md
rename to docs/modescope_pipeline/modelscope_usages.md
diff --git a/docs/modescope_pipeline/punc_pipeline.md b/docs/modescope_pipeline/punc_pipeline.md
new file mode 100644
index 0000000..cb81871
--- /dev/null
+++ b/docs/modescope_pipeline/punc_pipeline.md
@@ -0,0 +1,14 @@
+# Speech Recognition
+
+## Inference with pipeline
+### Quick start
+#### Inference with you data
+#### Inference with multi-threads on CPU
+#### Inference with multi GPU
+
+## Finetune with pipeline
+### Quick start
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/docs/modescope_pipeline/quick_start.md b/docs/modescope_pipeline/quick_start.md
new file mode 100644
index 0000000..a585cf6
--- /dev/null
+++ b/docs/modescope_pipeline/quick_start.md
@@ -0,0 +1,6 @@
+# Speech Recognition
+
+## Inference with pipeline
+
+
+## Finetune with pipeline
diff --git a/docs/modescope_pipeline/sv_pipeline.md b/docs/modescope_pipeline/sv_pipeline.md
new file mode 100644
index 0000000..cb81871
--- /dev/null
+++ b/docs/modescope_pipeline/sv_pipeline.md
@@ -0,0 +1,14 @@
+# Speech Recognition
+
+## Inference with pipeline
+### Quick start
+#### Inference with you data
+#### Inference with multi-threads on CPU
+#### Inference with multi GPU
+
+## Finetune with pipeline
+### Quick start
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/docs/modescope_pipeline/tp_pipeline.md b/docs/modescope_pipeline/tp_pipeline.md
new file mode 100644
index 0000000..cb81871
--- /dev/null
+++ b/docs/modescope_pipeline/tp_pipeline.md
@@ -0,0 +1,14 @@
+# Speech Recognition
+
+## Inference with pipeline
+### Quick start
+#### Inference with you data
+#### Inference with multi-threads on CPU
+#### Inference with multi GPU
+
+## Finetune with pipeline
+### Quick start
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/docs/modescope_pipeline/vad_pipeline.md b/docs/modescope_pipeline/vad_pipeline.md
new file mode 100644
index 0000000..cb81871
--- /dev/null
+++ b/docs/modescope_pipeline/vad_pipeline.md
@@ -0,0 +1,14 @@
+# Speech Recognition
+
+## Inference with pipeline
+### Quick start
+#### Inference with you data
+#### Inference with multi-threads on CPU
+#### Inference with multi GPU
+
+## Finetune with pipeline
+### Quick start
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/docs/onnxruntime_cpp.md b/docs/onnxruntime_cpp.md
deleted file mode 120000
index 1bb4529..0000000
--- a/docs/onnxruntime_cpp.md
+++ /dev/null
@@ -1 +0,0 @@
-../funasr/runtime/onnxruntime/readme.md
\ No newline at end of file
diff --git a/docs/asr_recipe.md b/docs/recipe/asr_recipe.md
similarity index 100%
rename from docs/asr_recipe.md
rename to docs/recipe/asr_recipe.md
diff --git a/docs/asr_recipe.md b/docs/recipe/lm_recipe.md
similarity index 100%
copy from docs/asr_recipe.md
copy to docs/recipe/lm_recipe.md
diff --git a/docs/punc_recipe.md b/docs/recipe/punc_recipe.md
similarity index 100%
rename from docs/punc_recipe.md
rename to docs/recipe/punc_recipe.md
diff --git a/docs/sv_recipe.md b/docs/recipe/sv_recipe.md
similarity index 100%
rename from docs/sv_recipe.md
rename to docs/recipe/sv_recipe.md
diff --git a/docs/vad_recipe.md b/docs/recipe/vad_recipe.md
similarity index 100%
rename from docs/vad_recipe.md
rename to docs/recipe/vad_recipe.md
diff --git a/docs/runtime/export.md b/docs/runtime/export.md
new file mode 120000
index 0000000..91f8b98
--- /dev/null
+++ b/docs/runtime/export.md
@@ -0,0 +1 @@
+../../funasr/export/README.md
\ No newline at end of file
diff --git a/docs/grpc_cpp.md b/docs/runtime/grpc_cpp.md
similarity index 100%
rename from docs/grpc_cpp.md
rename to docs/runtime/grpc_cpp.md
diff --git a/docs/runtime/grpc_python.md b/docs/runtime/grpc_python.md
new file mode 120000
index 0000000..ee8d6ea
--- /dev/null
+++ b/docs/runtime/grpc_python.md
@@ -0,0 +1 @@
+../../funasr/runtime/python/grpc/Readme.md
\ No newline at end of file
diff --git a/docs/libtorch_python.md b/docs/runtime/libtorch_python.md
similarity index 100%
rename from docs/libtorch_python.md
rename to docs/runtime/libtorch_python.md
diff --git a/docs/runtime/onnxruntime_cpp.md b/docs/runtime/onnxruntime_cpp.md
new file mode 120000
index 0000000..3661d18
--- /dev/null
+++ b/docs/runtime/onnxruntime_cpp.md
@@ -0,0 +1 @@
+../../funasr/runtime/onnxruntime/readme.md
\ No newline at end of file
diff --git a/docs/onnxruntime_python.md b/docs/runtime/onnxruntime_python.md
similarity index 100%
rename from docs/onnxruntime_python.md
rename to docs/runtime/onnxruntime_python.md
diff --git a/docs/runtime/websocket_python.md b/docs/runtime/websocket_python.md
new file mode 120000
index 0000000..0fabb85
--- /dev/null
+++ b/docs/runtime/websocket_python.md
@@ -0,0 +1 @@
+../../funasr/runtime/python/websocket/README.md
\ No newline at end of file
diff --git a/docs/websocket_python.md b/docs/websocket_python.md
deleted file mode 120000
index bcf239c..0000000
--- a/docs/websocket_python.md
+++ /dev/null
@@ -1 +0,0 @@
-../funasr/runtime/python/websocket/README.md
\ No newline at end of file
--
Gitblit v1.9.1